初始化

This commit is contained in:
zhu
2026-03-27 13:29:41 +08:00
commit ee03132cee
112 changed files with 6417 additions and 0 deletions

View File

@@ -0,0 +1,179 @@
"use strict";
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.decodeXML = exports.decodeHTMLStrict = exports.decodeHTML = exports.determineBranch = exports.BinTrieFlags = exports.fromCodePoint = exports.replaceCodePoint = exports.decodeCodePoint = exports.xmlDecodeTree = exports.htmlDecodeTree = void 0;
var decode_data_html_js_1 = __importDefault(require("./generated/decode-data-html.js"));
exports.htmlDecodeTree = decode_data_html_js_1.default;
var decode_data_xml_js_1 = __importDefault(require("./generated/decode-data-xml.js"));
exports.xmlDecodeTree = decode_data_xml_js_1.default;
var decode_codepoint_js_1 = __importDefault(require("./decode_codepoint.js"));
exports.decodeCodePoint = decode_codepoint_js_1.default;
var decode_codepoint_js_2 = require("./decode_codepoint.js");
Object.defineProperty(exports, "replaceCodePoint", { enumerable: true, get: function () { return decode_codepoint_js_2.replaceCodePoint; } });
Object.defineProperty(exports, "fromCodePoint", { enumerable: true, get: function () { return decode_codepoint_js_2.fromCodePoint; } });
var CharCodes;
(function (CharCodes) {
CharCodes[CharCodes["NUM"] = 35] = "NUM";
CharCodes[CharCodes["SEMI"] = 59] = "SEMI";
CharCodes[CharCodes["ZERO"] = 48] = "ZERO";
CharCodes[CharCodes["NINE"] = 57] = "NINE";
CharCodes[CharCodes["LOWER_A"] = 97] = "LOWER_A";
CharCodes[CharCodes["LOWER_F"] = 102] = "LOWER_F";
CharCodes[CharCodes["LOWER_X"] = 120] = "LOWER_X";
/** Bit that needs to be set to convert an upper case ASCII character to lower case */
CharCodes[CharCodes["To_LOWER_BIT"] = 32] = "To_LOWER_BIT";
})(CharCodes || (CharCodes = {}));
var BinTrieFlags;
(function (BinTrieFlags) {
BinTrieFlags[BinTrieFlags["VALUE_LENGTH"] = 49152] = "VALUE_LENGTH";
BinTrieFlags[BinTrieFlags["BRANCH_LENGTH"] = 16256] = "BRANCH_LENGTH";
BinTrieFlags[BinTrieFlags["JUMP_TABLE"] = 127] = "JUMP_TABLE";
})(BinTrieFlags = exports.BinTrieFlags || (exports.BinTrieFlags = {}));
function getDecoder(decodeTree) {
return function decodeHTMLBinary(str, strict) {
var ret = "";
var lastIdx = 0;
var strIdx = 0;
while ((strIdx = str.indexOf("&", strIdx)) >= 0) {
ret += str.slice(lastIdx, strIdx);
lastIdx = strIdx;
// Skip the "&"
strIdx += 1;
// If we have a numeric entity, handle this separately.
if (str.charCodeAt(strIdx) === CharCodes.NUM) {
// Skip the leading "&#". For hex entities, also skip the leading "x".
var start = strIdx + 1;
var base = 10;
var cp = str.charCodeAt(start);
if ((cp | CharCodes.To_LOWER_BIT) === CharCodes.LOWER_X) {
base = 16;
strIdx += 1;
start += 1;
}
do
cp = str.charCodeAt(++strIdx);
while ((cp >= CharCodes.ZERO && cp <= CharCodes.NINE) ||
(base === 16 &&
(cp | CharCodes.To_LOWER_BIT) >= CharCodes.LOWER_A &&
(cp | CharCodes.To_LOWER_BIT) <= CharCodes.LOWER_F));
if (start !== strIdx) {
var entity = str.substring(start, strIdx);
var parsed = parseInt(entity, base);
if (str.charCodeAt(strIdx) === CharCodes.SEMI) {
strIdx += 1;
}
else if (strict) {
continue;
}
ret += (0, decode_codepoint_js_1.default)(parsed);
lastIdx = strIdx;
}
continue;
}
var resultIdx = 0;
var excess = 1;
var treeIdx = 0;
var current = decodeTree[treeIdx];
for (; strIdx < str.length; strIdx++, excess++) {
treeIdx = determineBranch(decodeTree, current, treeIdx + 1, str.charCodeAt(strIdx));
if (treeIdx < 0)
break;
current = decodeTree[treeIdx];
var masked = current & BinTrieFlags.VALUE_LENGTH;
// If the branch is a value, store it and continue
if (masked) {
// If we have a legacy entity while parsing strictly, just skip the number of bytes
if (!strict || str.charCodeAt(strIdx) === CharCodes.SEMI) {
resultIdx = treeIdx;
excess = 0;
}
// The mask is the number of bytes of the value, including the current byte.
var valueLength = (masked >> 14) - 1;
if (valueLength === 0)
break;
treeIdx += valueLength;
}
}
if (resultIdx !== 0) {
var valueLength = (decodeTree[resultIdx] & BinTrieFlags.VALUE_LENGTH) >> 14;
ret +=
valueLength === 1
? String.fromCharCode(decodeTree[resultIdx] & ~BinTrieFlags.VALUE_LENGTH)
: valueLength === 2
? String.fromCharCode(decodeTree[resultIdx + 1])
: String.fromCharCode(decodeTree[resultIdx + 1], decodeTree[resultIdx + 2]);
lastIdx = strIdx - excess + 1;
}
}
return ret + str.slice(lastIdx);
};
}
function determineBranch(decodeTree, current, nodeIdx, char) {
var branchCount = (current & BinTrieFlags.BRANCH_LENGTH) >> 7;
var jumpOffset = current & BinTrieFlags.JUMP_TABLE;
// Case 1: Single branch encoded in jump offset
if (branchCount === 0) {
return jumpOffset !== 0 && char === jumpOffset ? nodeIdx : -1;
}
// Case 2: Multiple branches encoded in jump table
if (jumpOffset) {
var value = char - jumpOffset;
return value < 0 || value >= branchCount
? -1
: decodeTree[nodeIdx + value] - 1;
}
// Case 3: Multiple branches encoded in dictionary
// Binary search for the character.
var lo = nodeIdx;
var hi = lo + branchCount - 1;
while (lo <= hi) {
var mid = (lo + hi) >>> 1;
var midVal = decodeTree[mid];
if (midVal < char) {
lo = mid + 1;
}
else if (midVal > char) {
hi = mid - 1;
}
else {
return decodeTree[mid + branchCount];
}
}
return -1;
}
exports.determineBranch = determineBranch;
var htmlDecoder = getDecoder(decode_data_html_js_1.default);
var xmlDecoder = getDecoder(decode_data_xml_js_1.default);
/**
* Decodes an HTML string, allowing for entities not terminated by a semi-colon.
*
* @param str The string to decode.
* @returns The decoded string.
*/
function decodeHTML(str) {
return htmlDecoder(str, false);
}
exports.decodeHTML = decodeHTML;
/**
* Decodes an HTML string, requiring all entities to be terminated by a semi-colon.
*
* @param str The string to decode.
* @returns The decoded string.
*/
function decodeHTMLStrict(str) {
return htmlDecoder(str, true);
}
exports.decodeHTMLStrict = decodeHTMLStrict;
/**
* Decodes an XML string, requiring all entities to be terminated by a semi-colon.
*
* @param str The string to decode.
* @returns The decoded string.
*/
function decodeXML(str) {
return xmlDecoder(str, true);
}
exports.decodeXML = decodeXML;
//# sourceMappingURL=decode.js.map

View File

@@ -0,0 +1,60 @@
"use strict";
// Adapted from https://github.com/mathiasbynens/he/blob/36afe179392226cf1b6ccdb16ebbb7a5a844d93a/src/he.js#L106-L134
var _a;
Object.defineProperty(exports, "__esModule", { value: true });
exports.replaceCodePoint = exports.fromCodePoint = void 0;
var decodeMap = new Map([
[0, 65533],
[128, 8364],
[130, 8218],
[131, 402],
[132, 8222],
[133, 8230],
[134, 8224],
[135, 8225],
[136, 710],
[137, 8240],
[138, 352],
[139, 8249],
[140, 338],
[142, 381],
[145, 8216],
[146, 8217],
[147, 8220],
[148, 8221],
[149, 8226],
[150, 8211],
[151, 8212],
[152, 732],
[153, 8482],
[154, 353],
[155, 8250],
[156, 339],
[158, 382],
[159, 376],
]);
exports.fromCodePoint =
// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition, node/no-unsupported-features/es-builtins
(_a = String.fromCodePoint) !== null && _a !== void 0 ? _a : function (codePoint) {
var output = "";
if (codePoint > 0xffff) {
codePoint -= 0x10000;
output += String.fromCharCode(((codePoint >>> 10) & 0x3ff) | 0xd800);
codePoint = 0xdc00 | (codePoint & 0x3ff);
}
output += String.fromCharCode(codePoint);
return output;
};
function replaceCodePoint(codePoint) {
var _a;
if ((codePoint >= 0xd800 && codePoint <= 0xdfff) || codePoint > 0x10ffff) {
return 0xfffd;
}
return (_a = decodeMap.get(codePoint)) !== null && _a !== void 0 ? _a : codePoint;
}
exports.replaceCodePoint = replaceCodePoint;
function decodeCodePoint(codePoint) {
return (0, exports.fromCodePoint)(replaceCodePoint(codePoint));
}
exports.default = decodeCodePoint;
//# sourceMappingURL=decode_codepoint.js.map

View File

@@ -0,0 +1,77 @@
"use strict";
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.encodeNonAsciiHTML = exports.encodeHTML = void 0;
var encode_html_js_1 = __importDefault(require("./generated/encode-html.js"));
var escape_js_1 = require("./escape.js");
var htmlReplacer = /[\t\n!-,./:-@[-`\f{-}$\x80-\uFFFF]/g;
/**
* Encodes all characters in the input using HTML entities. This includes
* characters that are valid ASCII characters in HTML documents, such as `#`.
*
* To get a more compact output, consider using the `encodeNonAsciiHTML`
* function, which will only encode characters that are not valid in HTML
* documents, as well as non-ASCII characters.
*
* If a character has no equivalent entity, a numeric hexadecimal reference
* (eg. `&#xfc;`) will be used.
*/
function encodeHTML(data) {
return encodeHTMLTrieRe(htmlReplacer, data);
}
exports.encodeHTML = encodeHTML;
/**
* Encodes all non-ASCII characters, as well as characters not valid in HTML
* documents using HTML entities. This function will not encode characters that
* are valid in HTML documents, such as `#`.
*
* If a character has no equivalent entity, a numeric hexadecimal reference
* (eg. `&#xfc;`) will be used.
*/
function encodeNonAsciiHTML(data) {
return encodeHTMLTrieRe(escape_js_1.xmlReplacer, data);
}
exports.encodeNonAsciiHTML = encodeNonAsciiHTML;
function encodeHTMLTrieRe(regExp, str) {
var ret = "";
var lastIdx = 0;
var match;
while ((match = regExp.exec(str)) !== null) {
var i = match.index;
ret += str.substring(lastIdx, i);
var char = str.charCodeAt(i);
var next = encode_html_js_1.default.get(char);
if (typeof next === "object") {
// We are in a branch. Try to match the next char.
if (i + 1 < str.length) {
var nextChar = str.charCodeAt(i + 1);
var value = typeof next.n === "number"
? next.n === nextChar
? next.o
: undefined
: next.n.get(nextChar);
if (value !== undefined) {
ret += value;
lastIdx = regExp.lastIndex += 1;
continue;
}
}
next = next.v;
}
// We might have a tree node without a value; skip and use a numeric entitiy.
if (next !== undefined) {
ret += next;
lastIdx = i + 1;
}
else {
var cp = (0, escape_js_1.getCodePoint)(str, i);
ret += "&#x".concat(cp.toString(16), ";");
// Increase by 1 if we have a surrogate pair
lastIdx = regExp.lastIndex += Number(cp !== char);
}
}
return ret + str.substr(lastIdx);
}
//# sourceMappingURL=encode.js.map

View File

@@ -0,0 +1,112 @@
"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.escapeText = exports.escapeAttribute = exports.escapeUTF8 = exports.escape = exports.encodeXML = exports.getCodePoint = exports.xmlReplacer = void 0;
exports.xmlReplacer = /["&'<>$\x80-\uFFFF]/g;
var xmlCodeMap = new Map([
[34, "&quot;"],
[38, "&amp;"],
[39, "&apos;"],
[60, "&lt;"],
[62, "&gt;"],
]);
// For compatibility with node < 4, we wrap `codePointAt`
exports.getCodePoint =
// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
String.prototype.codePointAt != null
? function (str, index) { return str.codePointAt(index); }
: // http://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
function (c, index) {
return (c.charCodeAt(index) & 0xfc00) === 0xd800
? (c.charCodeAt(index) - 0xd800) * 0x400 +
c.charCodeAt(index + 1) -
0xdc00 +
0x10000
: c.charCodeAt(index);
};
/**
* Encodes all non-ASCII characters, as well as characters not valid in XML
* documents using XML entities.
*
* If a character has no equivalent entity, a
* numeric hexadecimal reference (eg. `&#xfc;`) will be used.
*/
function encodeXML(str) {
var ret = "";
var lastIdx = 0;
var match;
while ((match = exports.xmlReplacer.exec(str)) !== null) {
var i = match.index;
var char = str.charCodeAt(i);
var next = xmlCodeMap.get(char);
if (next !== undefined) {
ret += str.substring(lastIdx, i) + next;
lastIdx = i + 1;
}
else {
ret += "".concat(str.substring(lastIdx, i), "&#x").concat((0, exports.getCodePoint)(str, i).toString(16), ";");
// Increase by 1 if we have a surrogate pair
lastIdx = exports.xmlReplacer.lastIndex += Number((char & 0xfc00) === 0xd800);
}
}
return ret + str.substr(lastIdx);
}
exports.encodeXML = encodeXML;
/**
* Encodes all non-ASCII characters, as well as characters not valid in XML
* documents using numeric hexadecimal reference (eg. `&#xfc;`).
*
* Have a look at `escapeUTF8` if you want a more concise output at the expense
* of reduced transportability.
*
* @param data String to escape.
*/
exports.escape = encodeXML;
function getEscaper(regex, map) {
return function escape(data) {
var match;
var lastIdx = 0;
var result = "";
while ((match = regex.exec(data))) {
if (lastIdx !== match.index) {
result += data.substring(lastIdx, match.index);
}
// We know that this chararcter will be in the map.
result += map.get(match[0].charCodeAt(0));
// Every match will be of length 1
lastIdx = match.index + 1;
}
return result + data.substring(lastIdx);
};
}
/**
* Encodes all characters not valid in XML documents using XML entities.
*
* Note that the output will be character-set dependent.
*
* @param data String to escape.
*/
exports.escapeUTF8 = getEscaper(/[&<>'"]/g, xmlCodeMap);
/**
* Encodes all characters that have to be escaped in HTML attributes,
* following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
*
* @param data String to escape.
*/
exports.escapeAttribute = getEscaper(/["&\u00A0]/g, new Map([
[34, "&quot;"],
[38, "&amp;"],
[160, "&nbsp;"],
]));
/**
* Encodes all characters that have to be escaped in HTML text,
* following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
*
* @param data String to escape.
*/
exports.escapeText = getEscaper(/[&<>\u00A0]/g, new Map([
[38, "&amp;"],
[60, "&lt;"],
[62, "&gt;"],
[160, "&nbsp;"],
]));
//# sourceMappingURL=escape.js.map

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,9 @@
"use strict";
// Generated using scripts/write-decode-map.ts
Object.defineProperty(exports, "__esModule", { value: true });
exports.default = new Uint16Array(
// prettier-ignore
"\u0200aglq\t\x15\x18\x1b\u026d\x0f\0\0\x12p;\u4026os;\u4027t;\u403et;\u403cuot;\u4022"
.split("")
.map(function (c) { return c.charCodeAt(0); }));
//# sourceMappingURL=decode-data-xml.js.map

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,137 @@
"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.decodeXMLStrict = exports.decodeHTML5Strict = exports.decodeHTML4Strict = exports.decodeHTML5 = exports.decodeHTML4 = exports.decodeHTMLStrict = exports.decodeHTML = exports.decodeXML = exports.encodeHTML5 = exports.encodeHTML4 = exports.encodeNonAsciiHTML = exports.encodeHTML = exports.escapeText = exports.escapeAttribute = exports.escapeUTF8 = exports.escape = exports.encodeXML = exports.encode = exports.decodeStrict = exports.decode = exports.EncodingMode = exports.DecodingMode = exports.EntityLevel = void 0;
var decode_js_1 = require("./decode.js");
var encode_js_1 = require("./encode.js");
var escape_js_1 = require("./escape.js");
/** The level of entities to support. */
var EntityLevel;
(function (EntityLevel) {
/** Support only XML entities. */
EntityLevel[EntityLevel["XML"] = 0] = "XML";
/** Support HTML entities, which are a superset of XML entities. */
EntityLevel[EntityLevel["HTML"] = 1] = "HTML";
})(EntityLevel = exports.EntityLevel || (exports.EntityLevel = {}));
/** Determines whether some entities are allowed to be written without a trailing `;`. */
var DecodingMode;
(function (DecodingMode) {
/** Support legacy HTML entities. */
DecodingMode[DecodingMode["Legacy"] = 0] = "Legacy";
/** Do not support legacy HTML entities. */
DecodingMode[DecodingMode["Strict"] = 1] = "Strict";
})(DecodingMode = exports.DecodingMode || (exports.DecodingMode = {}));
var EncodingMode;
(function (EncodingMode) {
/**
* The output is UTF-8 encoded. Only characters that need escaping within
* XML will be escaped.
*/
EncodingMode[EncodingMode["UTF8"] = 0] = "UTF8";
/**
* The output consists only of ASCII characters. Characters that need
* escaping within HTML, and characters that aren't ASCII characters will
* be escaped.
*/
EncodingMode[EncodingMode["ASCII"] = 1] = "ASCII";
/**
* Encode all characters that have an equivalent entity, as well as all
* characters that are not ASCII characters.
*/
EncodingMode[EncodingMode["Extensive"] = 2] = "Extensive";
/**
* Encode all characters that have to be escaped in HTML attributes,
* following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
*/
EncodingMode[EncodingMode["Attribute"] = 3] = "Attribute";
/**
* Encode all characters that have to be escaped in HTML text,
* following {@link https://html.spec.whatwg.org/multipage/parsing.html#escapingString}.
*/
EncodingMode[EncodingMode["Text"] = 4] = "Text";
})(EncodingMode = exports.EncodingMode || (exports.EncodingMode = {}));
/**
* Decodes a string with entities.
*
* @param data String to decode.
* @param options Decoding options.
*/
function decode(data, options) {
if (options === void 0) { options = EntityLevel.XML; }
var opts = typeof options === "number" ? { level: options } : options;
if (opts.level === EntityLevel.HTML) {
if (opts.mode === DecodingMode.Strict) {
return (0, decode_js_1.decodeHTMLStrict)(data);
}
return (0, decode_js_1.decodeHTML)(data);
}
return (0, decode_js_1.decodeXML)(data);
}
exports.decode = decode;
/**
* Decodes a string with entities. Does not allow missing trailing semicolons for entities.
*
* @param data String to decode.
* @param options Decoding options.
* @deprecated Use `decode` with the `mode` set to `Strict`.
*/
function decodeStrict(data, options) {
if (options === void 0) { options = EntityLevel.XML; }
var opts = typeof options === "number" ? { level: options } : options;
if (opts.level === EntityLevel.HTML) {
if (opts.mode === DecodingMode.Legacy) {
return (0, decode_js_1.decodeHTML)(data);
}
return (0, decode_js_1.decodeHTMLStrict)(data);
}
return (0, decode_js_1.decodeXML)(data);
}
exports.decodeStrict = decodeStrict;
/**
* Encodes a string with entities.
*
* @param data String to encode.
* @param options Encoding options.
*/
function encode(data, options) {
if (options === void 0) { options = EntityLevel.XML; }
var opts = typeof options === "number" ? { level: options } : options;
// Mode `UTF8` just escapes XML entities
if (opts.mode === EncodingMode.UTF8)
return (0, escape_js_1.escapeUTF8)(data);
if (opts.mode === EncodingMode.Attribute)
return (0, escape_js_1.escapeAttribute)(data);
if (opts.mode === EncodingMode.Text)
return (0, escape_js_1.escapeText)(data);
if (opts.level === EntityLevel.HTML) {
if (opts.mode === EncodingMode.ASCII) {
return (0, encode_js_1.encodeNonAsciiHTML)(data);
}
return (0, encode_js_1.encodeHTML)(data);
}
// ASCII and Extensive are equivalent
return (0, escape_js_1.encodeXML)(data);
}
exports.encode = encode;
var escape_js_2 = require("./escape.js");
Object.defineProperty(exports, "encodeXML", { enumerable: true, get: function () { return escape_js_2.encodeXML; } });
Object.defineProperty(exports, "escape", { enumerable: true, get: function () { return escape_js_2.escape; } });
Object.defineProperty(exports, "escapeUTF8", { enumerable: true, get: function () { return escape_js_2.escapeUTF8; } });
Object.defineProperty(exports, "escapeAttribute", { enumerable: true, get: function () { return escape_js_2.escapeAttribute; } });
Object.defineProperty(exports, "escapeText", { enumerable: true, get: function () { return escape_js_2.escapeText; } });
var encode_js_2 = require("./encode.js");
Object.defineProperty(exports, "encodeHTML", { enumerable: true, get: function () { return encode_js_2.encodeHTML; } });
Object.defineProperty(exports, "encodeNonAsciiHTML", { enumerable: true, get: function () { return encode_js_2.encodeNonAsciiHTML; } });
// Legacy aliases (deprecated)
Object.defineProperty(exports, "encodeHTML4", { enumerable: true, get: function () { return encode_js_2.encodeHTML; } });
Object.defineProperty(exports, "encodeHTML5", { enumerable: true, get: function () { return encode_js_2.encodeHTML; } });
var decode_js_2 = require("./decode.js");
Object.defineProperty(exports, "decodeXML", { enumerable: true, get: function () { return decode_js_2.decodeXML; } });
Object.defineProperty(exports, "decodeHTML", { enumerable: true, get: function () { return decode_js_2.decodeHTML; } });
Object.defineProperty(exports, "decodeHTMLStrict", { enumerable: true, get: function () { return decode_js_2.decodeHTMLStrict; } });
// Legacy aliases (deprecated)
Object.defineProperty(exports, "decodeHTML4", { enumerable: true, get: function () { return decode_js_2.decodeHTML; } });
Object.defineProperty(exports, "decodeHTML5", { enumerable: true, get: function () { return decode_js_2.decodeHTML; } });
Object.defineProperty(exports, "decodeHTML4Strict", { enumerable: true, get: function () { return decode_js_2.decodeHTMLStrict; } });
Object.defineProperty(exports, "decodeHTML5Strict", { enumerable: true, get: function () { return decode_js_2.decodeHTMLStrict; } });
Object.defineProperty(exports, "decodeXMLStrict", { enumerable: true, get: function () { return decode_js_2.decodeXML; } });
//# sourceMappingURL=index.js.map